Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    quote followed by slash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    뮐
    1.17
    راتكم
    1.12
     Civilization
    1.10
    是
    1.08
     civilization
    1.08
     '~
    1.07
    ᠴ
    1.06
     tessel
    1.06
     ariel
    1.05
    <unused973>
    1.05
    POSITIVE LOGITS
     শক
    0.84
    wake
    0.83
     Pří
    0.82
     precondition
    0.80
    NH
    0.80
    к
    0.80
     NAM
    0.79
     girth
    0.78
     Nghi
    0.77
     stake
    0.77
    Act Density 0.001%

    No Known Activations